Machine Learning Techniques for Identity Document Verification in Uncontrolled Environments: A Case Study
- 17 June 2020
- book chapter
- conference paper
- Published by Springer Science and Business Media LLC
- Vol. 12088, 271-281
- https://doi.org/10.1007/978-3-030-49076-8_26
Abstract
Distributed (i.e. mobile) enrollment to services such as banking is gaining popularity. In such processes, users are often asked to provide proof of identity by taking a picture of an ID. For this to work securely, it is critical to automatically check basic document features, perform text recognition, among others. Furthermore, challenging contexts might arise, such as various backgrounds, diverse light quality, angles, perspectives, etc. In this paper we present a machine-learning based pipeline to process pictures of documents in such scenarios, that relies on various analysis modules and visual features for verification of document type and legitimacy. We evaluate our approach using identity documents from the Republic of Colombia. As a result, our machine learning background detection method achieved an accuracy of 98.4%, and our authenticity classifier an accuracy of 97.7% and an F1-score of 0.974.Keywords
This publication has 15 references indexed in Scilit:
- An Automatic Reader of Identity DocumentsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- MIDV-500: a dataset for identity document analysis and recognition on mobile devices in video streamComputer Optics, 2019
- Automatic Privacy Detection in Scanned Document Images Based on Deep Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2019
- A New Descriptor for Pattern Matching: Application to Identity Document VerificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2018
- Smart IDReader: Document Recognition in Video StreamPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Complex Document Classification and Localization Application on Identity Document ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- SmartDoc 2017 Video Capture: Mobile Document Acquisition in Video ModePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- ICDAR2015 competition on smartphone document capture and OCR (SmartDoc)Published by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Efficient use of local edge histogram descriptorPublished by Association for Computing Machinery (ACM) ,2000
- Comparing images using color coherence vectorsPublished by Association for Computing Machinery (ACM) ,1996